--- /dev/null
+From: Eric Dumazet <edumazet@google.com>
+Date: Sat, 4 Jun 2016 12:55:13 -0700
+Subject: [PATCH] fq_codel: fix NET_XMIT_CN behavior
+
+My prior attempt to fix the backlogs of parents failed.
+
+If we return NET_XMIT_CN, our parents wont increase their backlog,
+so our qdisc_tree_reduce_backlog() should take this into account.
+
+v2: Florian Westphal pointed out that we could drop the packet,
+so we need to save qdisc_pkt_len(skb) in a temp variable before
+calling fq_codel_drop()
+
+Fixes: 9d18562a2278 ("fq_codel: add batch ability to fq_codel_drop()")
+Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too")
+Reported-by: Stas Nichiporovich <stasn77@gmail.com>
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Cc: WANG Cong <xiyou.wangcong@gmail.com>
+Cc: Jamal Hadi Salim <jhs@mojatatu.com>
+---
+
+--- a/net/sched/sch_fq_codel.c
++++ b/net/sched/sch_fq_codel.c
+@@ -197,6 +197,7 @@ static int fq_codel_enqueue(struct sk_bu
+ unsigned int idx, prev_backlog, prev_qlen;
+ struct fq_codel_flow *flow;
+ int uninitialized_var(ret);
++ unsigned int pkt_len;
+ bool memory_limited;
+
+ idx = fq_codel_classify(skb, sch, &ret);
+@@ -228,6 +229,8 @@ static int fq_codel_enqueue(struct sk_bu
+ prev_backlog = sch->qstats.backlog;
+ prev_qlen = sch->q.qlen;
+
++ /* save this packet length as it might be dropped by fq_codel_drop() */
++ pkt_len = qdisc_pkt_len(skb);
+ /* fq_codel_drop() is quite expensive, as it performs a linear search
+ * in q->backlogs[] to find a fat flow.
+ * So instead of dropping a single packet, drop half of its backlog
+@@ -235,14 +238,23 @@ static int fq_codel_enqueue(struct sk_bu
+ */
+ ret = fq_codel_drop(sch, q->drop_batch_size);
+
+- q->drop_overlimit += prev_qlen - sch->q.qlen;
++ prev_qlen -= sch->q.qlen;
++ prev_backlog -= sch->qstats.backlog;
++ q->drop_overlimit += prev_qlen;
+ if (memory_limited)
+- q->drop_overmemory += prev_qlen - sch->q.qlen;
+- /* As we dropped packet(s), better let upper stack know this */
+- qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen,
+- prev_backlog - sch->qstats.backlog);
++ q->drop_overmemory += prev_qlen;
+
+- return ret == idx ? NET_XMIT_CN : NET_XMIT_SUCCESS;
++ /* As we dropped packet(s), better let upper stack know this.
++ * If we dropped a packet for this flow, return NET_XMIT_CN,
++ * but in this case, our parents wont increase their backlogs.
++ */
++ if (ret == idx) {
++ qdisc_tree_reduce_backlog(sch, prev_qlen - 1,
++ prev_backlog - pkt_len);
++ return NET_XMIT_CN;
++ }
++ qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog);
++ return NET_XMIT_SUCCESS;
+ }
+
+ /* This is the specific function called from codel_dequeue()
device, it has to decide which ones to send first, which ones to
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
-@@ -676,7 +676,7 @@ static const struct Qdisc_class_ops fq_c
+@@ -688,7 +688,7 @@ static const struct Qdisc_class_ops fq_c
.walk = fq_codel_walk,
};
.cl_ops = &fq_codel_class_ops,
.id = "fq_codel",
.priv_size = sizeof(struct fq_codel_sched_data),
-@@ -692,6 +692,7 @@ static struct Qdisc_ops fq_codel_qdisc_o
+@@ -704,6 +704,7 @@ static struct Qdisc_ops fq_codel_qdisc_o
.dump_stats = fq_codel_dump_stats,
.owner = THIS_MODULE,
};